The Do-Nothing App That Passed Every Test
I wrote a program that does nothing. The test suite generated to check an app rebuild gave it a perfect score.
AI researcher and builder
I research how AI systems fail, and I build with them.
I write papers on how to test AI systems, build products and agent tools, and contribute to open source. I report failures next to passes. By day I build AI tooling at CHG Healthcare, and I run Skora, a college admissions platform.
How AI gets checked.
Three papers so far, on coding-agent verification and on machine-learning evaluation in finance. Each one reports what failed.
Products and agents.
A college admissions platform, a collectibles marketplace, an AI receptionist, a business stress-test tool and a published Roblox game.
Tools in public.
Merged fixes to the OpenClaw agent framework, small agent tools such as custody and Skill-Drift, talks, and a youth coding competition I ran.
Selected result
A coding agent can rebuild an app until every test goes green. When one pipeline writes both the spec and the tests, they can share the same blind spot, so green says less than it appears to. My work measures that gap and proposes ways to audit it.
I wrote a program that does nothing. The test suite generated to check an app rebuild gave it a perfect score.
A rebuilt Express API passed every generated check. It also changed where clients had to put a user's name.
The generated test found three strings. A coding agent returned a page with those strings and no usable todo list.
Also in progress: Experience Without Permission, a book on how AI changes the way beginners become experts.
An open-source MCP server that extracts contracts and tests from an existing app so a fresh coding agent can rebuild it from a spec. The paper reports the runs that worked and the ones that failed.
When one pipeline writes both the spec and the acceptance tests, they share a blind spot. A do-nothing stub passed every generated test across 30 frozen rebuilds. The paper proposes a three-step audit to run before trusting a green rebuild.
A model’s accuracy score barely moved (0.553 to 0.551), yet 61.1% of the stocks it picked changed. An audit of how a stable metric can sit on top of unstable decisions.
Records what an app does before an AI agent rebuilds it, so the agent has a spec to work from and a test suite you can audit. The papers report where that process catches problems and where a green run still hides them.
Students see their estimated chances at each college, get matched to schools and get feedback on essays. Counselors manage their students and offer Skora under their own brand. College facts come from College Scorecard and IPEDS data. Essay feedback is drafted by AI and reviewed by a counselor. I am the CEO.
A marketplace and portfolio tracker for Pokémon card collectors. Search a card database, track what a collection is worth, and trade or sell with other collectors. Card scanning runs on the collector’s own device. It is also the app behind the 30 frozen rebuilds in the Rebuild Dossier study.
Answers a small business’s calls and texts using the business’s own documents. It started when an HVAC chatbot I was testing invented a coupon that appeared nowhere in its source material. That turned my attention to grounding and AI reliability.
Five minutes on why building has become easier, why judgment still takes real-world feedback, and what that means for how beginners learn.
The Rebuild Dossier results on agent rebuild testing, including the stub that passed every generated test.
Email is the fastest way to reach me. I welcome replication attempts, technical feedback and invitations to speak or write.